.. |
__pycache__
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
data
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
fp16_deprecated
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
fused_kernels
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
model
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
mpu
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
optimizer
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
tokenizer
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
__init__.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
arguments.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
checkpointing.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
global_vars.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
indexer.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
initialize.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
learning_rates.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
memory.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
microbatches.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
p2p_communication.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
package_info.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
schedules.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
text_generation_utils.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
training.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
training_original.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |
utils.py
|
a807fe3a90
Swedish GPTBootcamp tutorials
|
3 years ago |